sota-sandboxing SKILL.md skillA
sota-sandboxing from martinholovsky/sota-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add martinholovsky/sota-skills/sota-sandboxing@git:20261026.808c340Pins git:20261026.808c340 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- martinholovsky/sota-skills
- Path
skills/sota-sandboxing/SKILL.md- Versions recorded
- 8
- Latest version
- git:20261026.808c340, committed Oct 26, 2026
- First version recorded
- Jun 17, 2026
- Size
- 10,013 bytes
- Repository stars
- 26
- License
- CC-BY-4.0
State-of-the-art sandboxing and isolation engineering (2026). Use when designing isolation for untrusted code, untrusted input parsing, multi-tenant workloads, or AI/agent execution — and when auditing existing systems for isolation gaps. Covers least privilege, defense in depth, isolation boundary selection (VM/microVM/gVisor/container/process/WASM), Linux primitives (namespaces, cgroups v2, seccomp-bpf, Landlock, AppArmor/SELinux, capabilities), Docker/OCI and Kubernetes hardening, privilege…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# SOTA Sandboxing & Isolation ## Purpose Engineer and audit isolation boundaries so that compromise of a workload — untrusted code, a parser fed attacker bytes, a tenant, or an AI agent — is contained by design. The skill encodes 2026 state of the art: allowlist-first least privilege, boundary strength matched to threat class, kernel primitives composed correctly, hardened container/microVM deployment, application-level privilege separation, and agent-specific containment (lethal trifecta, egress control, ephemeral execution). Two modes. Pick one explicitly at the start of the task. --- ## BUILD mode Use when designing or implementing isolation for new or changed workloads. 1. **Classify the threat** before any mechanism talk: untrusted CODE, untrusted INPUT, or MULTI-TENANT ([`rules/01`](rules/01-isolation-boundaries.md) §3). State the classification in your output. 2. **Pick the boundary floor** from the decision table in [`rules/01`](rules/01-isolation-boundaries.md); never go below it silently. If constraints force a weaker boundary, write the risk acceptance into the design. 3. **Enumerate needs first** — files, syscalls, network destinations, CPU/memory/ …
Read the whole file at its exact version.
How to install
mdr add martinholovsky/sota-skills/sota-sandboxing@sha256:1fd5ba14fefcea53The line at the top of this page pins the label git:20261026.808c340, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_nc477625fozrxpev)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Jun 17, 2026 and Oct 26, 2026, about one every 19 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261026.808c340 latest | 2026-10-26 | 808c340 | 10,013 B | A | view · diff |
| git:20261024.8dd2b0a | 2026-10-24 | 8dd2b0a | 9,943 B | A | view · diff |
| git:20261023.7ad6939 | 2026-10-23 | 7ad6939 | 9,702 B | A | view · diff |
| git:20261012.293de9f | 2026-10-12 | 293de9f | 9,590 B | A | view · diff |
| git:20261012.ae1b29b | 2026-10-12 | ae1b29b | 9,407 B | A | view · diff |
| git:20260925.467e225 | 2026-09-25 | 467e225 | 8,979 B | A | view · diff |
| git:20260925.054c2cb | 2026-09-25 | 054c2cb | 8,585 B | A | view · diff |
| git:20260617.c5d2c7b | 2026-06-17 | c5d2c7b | 8,333 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10013 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
martinholovsky/sota-skills · 26 stars · license CC-BY-4.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_nc477625fozrxpev GET https://markdownregistry.com/api/v1/resolve?ref=martinholovsky/sota-skills/sota-sandboxing GET https://markdownregistry.com/api/v1/blob/1fd5ba14fefcea533e6375d89a7f8888efe9e79ce0d50a43e083e4d5015cb6ef
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.